Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     شعر
    -0.08
     hink
    -0.08
     hacking
    -0.08
     torno
    -0.07
     разб
    -0.07
     తీవ్ర
    -0.07
     cherry
    -0.07
     toppen
    -0.07
    orno
    -0.07
     Worst
    -0.07
    POSITIVE LOGITS
     역할
    0.15
    职责
    0.15
     निभ
    0.13
    作用
    0.13
     भूमिका
    0.13
     roles
    0.13
     role
    0.13
     desempen
    0.12
     ভূম
    0.12
     responsibilities
    0.12
    Act Density 0.102%

    No Known Activations